Serving Machine Learning Models with Redis & Apache Spark


Details
Free beer, pizza, swag & lots more!
Tague Griffith, Head of Developer Advocacy, Redis Labs
A Database Month event http://www.DBMonth.com/database/redis
In this action-packed session we will look at how Redis 4.0 and the Redis-ML module can be used out of the box to provide a real-time decision making service. Using Apache Spark, we will implement a machine learning pipeline and discuss the types of predictive models (decision trees, regressions, etc.) that are supported by Redis-ML.
You will also learn how to load Spark models into Redis using the available toolkit, and how to implement real-time decision making.
Making real-time decisions using predictive models is one of the key obstacles in successfully deploying a machine learning strategy. Building customer services to support reliable real-time decision making with scale can be a monumental challenge; by the end of this fun-filled session you will be empowered to architect such systems with ease and confidence.
Tague Griffith, Head of Developer Advocacy, Redis Labs
Tague Griffith, Head of Developer Advocacy at Redis Labs (http://www.redislabs.com/), has over 20 years of experience in Silicon Valley as a software engineer and architect building large scale distributed systems and infrastructure. He currently heads up the developer relations and advocacy program at Redis Labs.
Prior to joining Redis Labs, Tague held positions with Apple, Netscape, Yahoo/Flickr and GoPro. He has a BS and MS in Computer Science from Stanford University with a specialization in database systems.
Swag giveaway + food/drinks at 6:30pm
Power-Networking at 6:35pm
Presentation starts at 6:40pm
Did you know that Techie Youth (http://www.techieyouth.org/) is the ONLY charity providing career-opportunities to foster-kids (kids without parents) in NYC? Please look at https://www.TechieYouth.org (https://www.techieyouth.org/) to learn how you can help foster-kids who need you.

Serving Machine Learning Models with Redis & Apache Spark